User interface

1. A computer-implemented method comprising: receiving, by a computing device, typed input from a keyboard operatively coupled to the computing device; outputting, by the computing device and while continuing to receive typed input from the keyboard, a prompt that requests user selection of an action to be performed by the computing device, wherein the typed input received while outputting the prompt is not responsive to the prompt; receiving, by the computing device while outputting the prompt and while continuing to receive typed input from the keyboard, spoken input through a microphone operatively coupled to the computing device or visual input through a camera operatively coupled to the computing device; determining whether the spoken input or the visual input, that was received while the prompt was being output and while typed input was continuing to be received, is responsive to the prompt; and in response to a determination that the spoken input or the visual input, that was received while the prompt was being output and while typed input was continuing to be received, is responsive to the prompt, performing, by the computing device, an action corresponding to the spoken input or the visual input and ceasing to output the prompt.

2. The computer-implemented method of claim 1 , wherein: the computing device comprises a mobile computing device that includes a touch-sensitive display, the keyboard is a virtual keyboard that is displayed on the touch-sensitive display, and outputting the prompt comprises displaying the prompt on the touch-sensitive display.

3. The computer-implemented method of claim 2 , further comprising: identifying a term in the typed input that is determined to be likely misspelled, wherein outputting the prompt that requests user selection of the action to be performed by the computing device comprises (i) displaying an indication that the identified term has been determined to be likely misspelled, and (ii) providing a suggested spell-corrected term to replace the identified term, and wherein determining whether the spoken input or the visual input is responsive to the prompt comprises determining whether the spoken input or the visual input indicates user selection of an action to replace the identified term with the spell-corrected term.

4. The computer-implemented method of claim 3 , wherein the prompt, the virtual keyboard, and a text entry area that receives the typed input are concurrently displayed on the touch-sensitive display of the mobile computing device.

5. The computer-implemented method of claim 1 , wherein the prompt identifies a particular action to be performed by the computing device, and wherein determining whether the spoken input or the visual input is responsive to the prompt comprises determining whether the user has provided one of (i) an affirmance for the computing device to perform the particular action, and (ii) a selection to not perform the particular action identified by the prompt.

6. The computer-implemented method of claim 5 , wherein determining whether the user has provided one of (i) an affirmance for the computing device to perform the particular action, and (ii) a selection to not perform the particular action identified by the prompt comprises identifying, from the visual input, a nodding motion of a head or a shaking motion of the head, respectively.

7. The computer-implemented method of claim 1 , wherein determining whether the visual input is responsive to the prompt comprises determining whether a head movement is one of a nodding gesture and a shaking gesture.

8. The computer-implemented method of claim 1 , wherein determining whether the spoken input is responsive to the prompt comprises performing speech recognition on audio received through the microphone of the computing device.

9. The computer-implemented method of claim 1 , further comprising providing the typed input to a particular application that is executing on the computing device, wherein outputting the prompt comprises generating the prompt by the particular application that is executing on the computing device.

10. The computer-implemented method of claim 1 , wherein outputting the prompt does not interfere with receiving typed input through the keyboard of the computing device that is not responsive to the prompt.

11. One or more non-transitory computer-readable media having instructions stored thereon that, when executed by one or more computers, cause performance of operations comprising: receiving, by the one or more computers, typed input from a keyboard operatively coupled to the one or more computers; outputting, by the one or more computers and while continuing to receive typed input from the keyboard, a prompt that requests user selection of an action to be performed by the one or more computers, wherein the typed input received while outputting the prompt is not responsive to the prompt; receiving, by the one or more computers while outputting the prompt and while continuing to receive typed input from the keyboard, spoken input through a microphone operatively coupled to the one or more computers or visual input through a camera operatively coupled to the one or more computers; determining whether the spoken input or the visual input, that was received while the prompt was being output and while typed input was continuing to be received, is responsive to the prompt; and in response to a determination that the spoken input or the visual input, that was received while the prompt was being output and while typed input was continuing to be received, is responsive to the prompt, performing, by the one or more computers, an action corresponding to the spoken input or the visual input and ceasing to output the prompt.

12. The one or more non-transitory computer-readable media of claim 11 , wherein: the one or more computers comprises a mobile computing device that includes a touch-sensitive display, the keyboard is a virtual keyboard that is displayed on the touch-sensitive display, and outputting the prompt comprises displaying the prompt on the touch-sensitive display.

13. The one or more non-transitory computer-readable media of claim 12 , wherein the operations further comprise: identifying a term in the typed input that is determined to be likely misspelled, wherein outputting the prompt that requests user selection of the action to be performed by the one or more computers comprises (i) displaying an indication that the identified term has been determined to be likely misspelled, and (ii) providing a suggested spell-corrected term to replace the identified term, and wherein determining whether the spoken input or the visual input is responsive to the prompt comprises determining whether the spoken input or the visual input indicates user selection of an action to replace the identified term with the spell-corrected term.

14. The one or more non-transitory computer-readable media of claim 13 , wherein the prompt, the virtual keyboard, and a text entry area that receives the typed input are concurrently displayed on the touch-sensitive display of the mobile computing device.

15. The one or more non-transitory computer-readable media of claim 11 , wherein the prompt identifies a particular action to be performed by the one or more computers, and wherein determining whether the spoken input or the visual input is responsive to the prompt comprises determining whether the user has provided one of (i) an affirmance for the one or more computers to perform the particular action, and (ii) a selection to not perform the particular action identified by the prompt.

16. The one or more non-transitory computer-readable media of claim 15 , wherein determining whether the user has provided one of (i) an affirmance for the one or more computers to perform the particular action, and (ii) a selection to not perform the particular action identified by the prompt comprises identifying, from the visual input, a nodding motion of a head or a shaking motion of the head, respectively.

17. The one or more non-transitory computer-readable media of claim 11 , wherein determining whether the visual input is responsive to the prompt comprises determining whether a head movement is one of a nodding gesture and a shaking gesture.

18. The one or more non-transitory computer-readable media of claim 11 , wherein determining whether the spoken input is responsive to the prompt comprises performing speech recognition on audio received through the microphone of the one or more computers.

19. The one or more non-transitory computer-readable media of claim 11 , wherein the operations further comprise providing the typed input to a particular application that is executing on the one or more computers, wherein outputting the prompt comprises generating the prompt by the particular application that is executing on the one or more computers.

20. The one or more non-transitory computer-readable media of claim 11 , wherein outputting the prompt does not interfere with receiving typed input through the keyboard of the one or more computers that is not responsive to the prompt.

21. A system comprising: one or more computers; and one or more non-transitory computer-readable media having instructions stored thereon that, when executed by the one or more computers, cause the one or more computers to perform operations comprising: receiving, by the one or more computers, typed input from a keyboard operatively coupled to the one or more computers; outputting, by the one or more computers and while continuing to receive typed input from the keyboard, a prompt that requests user selection of an action to be performed by the one or more computers, wherein the typed input received while outputting the prompt is not responsive to the prompt; receiving, by the one or more computers while outputting the prompt and while continuing to receive typed input through the keyboard, spoken input through a microphone operatively coupled to the one or more computers or visual input through a camera operatively coupled to the one or more computers; determining whether the spoken input or the visual input, that was received while the prompt was being output and while typed input was continuing to be received, is responsive to the prompt; and in response to a determination that the spoken input or the visual input, that was received while the prompt was being output and while typed input was continuing to be received, is responsive to the prompt, performing, by the one or more computers, an action corresponding to the spoken input or the visual input and ceasing to output the prompt.